检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Miao, Wenjun Pang, Guansong Li, Tianqi Bai, Xiao Zheng, Jin School of Computer Science and Engineering Beihang University China School of Computing and Information Systems Singapore Management University Singapore State Key Laboratory of Software Development Environment Jiangxi Research Institute Beihang University China State Key Laboratory of Virtual Reality Technology and Systems Beihang University China

Existing out-of-distribution (OOD) methods have shown great success on balanced datasets but become ineffective in long-tailed recognition (LTR) scenarios where 1) OOD samples are often wrongly classified into head classes and/or 2) tail-class samples are treated as OOD samples. To address these issues, current studies fit a prior distribution of auxiliary/pseudo OOD data to the long-tailed in-distribution (ID) data. However, it is difficult to obtain such an accurate prior distribution given the unknowingness of real OOD samples and heavy class imbalance in LTR. A straightforward solution to avoid the requirement of this prior is to learn an outlier class to encapsulate the OOD samples. The main challenge is then to tackle the aforementioned confusion between OOD samples and head/tail-class samples when learning the outlier class. To this end, we introduce a novel calibrated outlier class learning (COCL) approach, in which 1) a debiased large margin learning method is introduced in the outlier class learning to distinguish OOD samples from both head and tail classes in the representation space and 2) an outlier-class-aware logit calibration method is defined to enhance the long-tailed classification confidence. Extensive empirical results on three popular benchmarks CIFAR10-LT, CIFAR100-LT, and ImageNet-LT demonstrate that COCL substantially outperforms state-of-the-art OOD detection methods in LTR while being able to improve the classification accuracy on ID data. Code is availab.e at https://***/mala-lab.COCL. Copyright © 2023, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

On Efficient Packet Batching and Resource Allocation for GPU based NFV Acceleration

On Efficient Packet Batching and Resource Allocation for GPU...

引用

International Workshop on Quality of Service

作者： Deze Zeng Andong Zhu Lin Gu Quan Chen Minyi Guo School of Computer Science China University of Geosciences Wuhan Hubei China State Key Lab. for Novel Software Technology Nanjing University Nanjing China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China

Network Function Virtualization (NFV) has already become an essential technology for improving the scalab.lity and flexibility of modern computer networks. The performance gap has become the main issue that impedes the development of NFV. GPUs, with massive parallel processors, are advocated to accelerate the Virtualized Network Functions (VNFs). However, the special architecture and workflow of GPUs introduce new challenges, especially on the batched processing, and resource allocation. In this paper, we propose GPU-based NFV Acceleration framework (GNFA) with an efficient packet batching and resource allocation solution. Considering the increased latency caused by the accumulation of the GPU kernel invoking overhead, we first invent a latency reduction mechanism called SM Performance Compensation (SPC). A Partition and Adjustment based Batching and Resource Allocation (PABARA) algorithm that jointly considers batch size tuning and GPU thread allocation is also proposed. We have practically implemented GNFA and extensively evaluated its performance on some well-known VNFs. The experiment results show that GNFA can effectively promote the GPU resource utilization and improve the NFV performance in terms of per-packet latency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TAM: A Computing in Memory based on Tandem Array within STT-MRAM for Energy-Efficient Analog MAC Operation

TAM: A Computing in Memory based on Tandem Array within STT-...

引用

Design, Automation and Test in Europe Conference and Exhibition

作者： Jinkai Wang Zhengkun Gu Hongyu Wang Zuolei Hao Bojun Zhang Weisheng Zhao Yue Zhang MIIT Key Laboratory of Spintronics Fert Beijing Institute School of Integrated Circuit Science and Engineering Beihang University Beijing China State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing China Nanoelectronics Science and Technology Center Hefei Innovation Research Institute Beihang University Hefei China

Computing in memory (CIM) has been demonstrated promising for energy efficient computing. However, the dramatic growth of the data scale in neural network processors has aroused a demand for CIM architecture of higher bit density, for which the spin transfer torque magnetic RAM (STT-MRAM) with high bit density and performance arises as an up-and-coming candidate solution. In this work, we propose an analog CIM scheme based on tandem array within STT-MRAM (TAM) to further improve energy efficiency while achieving high bit density. First, the resistance summation based analog MAC operation minimizes the effect of low tunnel magnetoresistance (TMR) by the serial magnetic tunnel junctions (MTJs) structure in the proposed tandem array with smaller area overhead. Moreover, a read scheme of resistive-to-binary is designed to achieve the MAC results accurately and reliably. Besides, the data-dependent error caused by MTJs in series has been eliminated with a proposed dynamic selection circuit. Simulation results of a 2Kb TAM architecture show 113.2 TOPS/W and 63.7 TOPS/W for 4-bit and 8-bit input/weight precision, respectively, and reduction by 39.3% for bit-cell area compared with existing array of MTJs in series.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TRANSFORMER-PATCHER: ONE MISTAKE WORTH ONE NEURON

arXiv

引用

arXiv 2023年

作者： Huang, Zeyu Shen, Yikang Zhang, Xiaofeng Zhou, Jie Rong, Wenge Xiong, Zhang State Key Laboratory of Software Development Environment Beihang University China Sino-French Engineer School Beihang University China School of Computer Science and Engineering Beihang University China Mila University of Montreal Canada WeChat AI Tencent Inc China

Large Transformer-based Pretrained Language Models (PLMs) dominate almost all Natural Language Processing (NLP) tasks. Nevertheless, they still make mistakes from time to time. For a model deployed in an industrial environment, fixing these mistakes quickly and robustly is vital to improve user experiences. Previous works formalize such problems as Model Editing (ME) and mostly focus on fixing one mistake. However, the one-mistake-fixing scenario is not an accurate abstraction of the real-world challenge. In the deployment of AI services, there are ever-emerging mistakes, and the same mistake may recur if not corrected in time. Thus a preferable solution is to rectify the mistakes as soon as they appear nonstop. Therefore, we extend the existing ME into Sequential Model Editing (SME) to help develop more practical editing methods. Our study shows that most current ME methods could yield unsatisfying results in this scenario. We then introduce Transformer-Patcher, a novel model editor that can shift the behavior of transformer-based models by simply adding and training a few neurons in the last Feed-Forward Network layer. Experimental results on both classification and generation tasks show that Transformer-Patcher can successively correct up to thousands of errors (Reliability) and generalize to their equivalent inputs (Generality) while retaining the model’s accuracy on irrelevant inputs (Locality). Our method outperforms previous fine-tuning and HyperNetwork-based methods and achieves state-of-the-art performance for Sequential Model Editing (SME). The code is availab.e at https://***/ZeroYuHuang/Transform er-Patcher. Copyright © 2023, The Authors. All rights reserved.

关键词： Network layers

来源：评论

学校读者我要写书评

暂无评论

Improving variational autoencoders with density gap-based regularization 22

Improving variational autoencoders with density gap-based re...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Jianfei Zhang Jun Bai Chenghua Lin Yanmeng Wang Wenge Rong State Key Laboratory of Software Development Environment Beihang University China and School of Computer Science and Engineering Beihang University China Department of Computer Science University of Sheffield United Kingdom Ping An Technology China

ISBN: (纸本)9781713871088

Variational autoencoders (VAEs) are one of the most powerful unsupervised learning frameworks in NLP for latent representation learning and latent-directed generation. The classic optimization goal of VAEs is to maximize the Evidence Lower Bound (ELBo), which consists of a conditional likelihood for generation and a negative Kullback-Leibler (KL) divergence for regularization. In practice, optimizing ELBo often leads the posterior distribution of all samples converging to the same degenerated local optimum, namely posterior collapse or KL vanishing. There are effective ways proposed to prevent posterior collapse in VAEs, but we observe that they in essence make trade-offs between posterior collapse and the hole problem, i.e., the mismatch between the aggregated posterior distribution and the prior distribution. To this end, we introduce new training objectives to tackle both problems through a novel regularization based on the probabilistic density gap between the aggregated posterior distribution and the prior distribution. Through experiments on language modeling, latent space visualization, and interpolation, we show that our proposed method can solve both problems effectively and thus outperforms the existing methods in latent-directed generation. To the best of our knowledge, we are the first to jointly solve the hole problem and posterior collapse.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving Variational Autoencoders with Density Gap-based Regularization

arXiv

引用

arXiv 2022年

作者： Zhang, Jianfei Bai, Jun Lin, Chenghua Wang, Yanmeng Rong, Wenge State Key Laboratory of Software Development Environment Beihang University China School of Computer Science and Engineering Beihang University China Department of Computer Science University of Sheffield United Kingdom Ping An Technology China

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

A Contrastive Learning Based Unsupervised Multi-View Stereo with Multi-Stage Self-Training Strategy

SSRN

引用

SSRN 2023年

作者： Wang, Zihang Luo, Haonan Wang, Xiang Zheng, Jin Ning, Xin Bai, Xiao School of Computer Science and Engineering State Key Laboratory of Software Development Environment Jiangxi Research Institute Beihang University Beijing100191 China School of Computer and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China Institute of Semiconductors Chinese Academy of Sciences Beijing100083 China

Recent years, unsupervised multi-view stereo methods have achieved excellent success that can produce comparable results to earlier supervised ***, as unsupervised MVS uses image reconstruction as pretext task, it faces two vital drawbacks: RGB value, which is the the measurement of image, is not robust enough across views due to complicated environment like lighting conditions and reconstruction itself cannot reflect quality of depth estimation *** problems cause the actual optimization goal to diverge from the expected optimization goal, thus could impair the training *** enhance robustness of pretext task, we propose a contrastive learning based *** constraint adds featuremetric consistency across views by forcing the features between matching points similar and the features between unmatched points *** add linear properties to overall training procedure, we propose a multi-stage training strategy that uses pseudo lab.l as supervision after unsupervised training at the *** the other hand, we adopt an iterative optimizer that proven to be quite effective in supervised MVS to accelerate ***, we conduct a series of experiments on the DTU dataset and Tanks and Temples dataset that demonstrate the efficiency and robustness of our method compared with the state-of-the-art methods. © 2023, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Towards Fully Decoupled End-to-End Person Search

Towards Fully Decoupled End-to-End Person Search

引用

Proceedings of the Digital Image Computing: Technqiues and Applications (DICTA)

作者： Pengcheng Zhang Xiao Bai Jin Zheng Xin Ning School of Computer Science and Engineering State Key Laboratory of Software Development Environment Jiangxi Research Institute Beihang University Beijing China Institute of Semiconductors Chinese Academy of Sciences Cognitive Computing Technology Joint Laboratory Wave Group Beijing China

End-to-end person search aims to jointly detect and re-identify a target person in raw scene images with a unified model. The detection task unifies all persons while the re-id task discriminates different identities, resulting in conflict optimal objectives. Existing works proposed to decouple end-to-end person search to alleviate such conflict. Yet these methods are still sub-optimal on one or two of the sub-tasks due to their partially decoupled models, which limits the overall person search performance. In this paper, we propose to fully decouple person search towards optimal person search. A task-incremental person search network is proposed to incrementally construct an end-to-end model for the detection and re-id sub-task, which decouples the model architecture for the two sub-tasks. The proposed task-incremental network allows task-incremental training for the two conflicting tasks. This enables independent learning for different objectives thus fully decoupled the model for personsearch. Comprehensive experimental evaluations demonstrate the effectiveness of the proposed fully decoupled models for end-to-end person search.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Fully Decoupled End-to-End Person Search

arXiv

引用

arXiv 2023年

作者： Zhang, Pengcheng Zheng, Jin Bai, Xiao Ning, Xin School of Computer Science and Engineering State Key Laboratory of Software Development Environment Jiangxi Research Institute Beihang University Beijing China Institute of Semiconductors Chinese Academy of Sciences Cognitive Computing Technology Joint Laboratory Wave Group Beijing China

End-to-end person search aims to jointly detect and re-identify a target person in raw scene images with a unified model. The detection task unifies all persons while the re-id task discriminates different identities, resulting in conflict optimal objectives. Existing works proposed to decouple end-to-end person search to alleviate such conflict. Yet these methods are still sub-optimal on one or two of the sub-tasks due to their partially decoupled models, which limits the overall person search performance. In this paper, we propose to fully decouple person search towards optimal person search. A task-incremental person search network is proposed to incrementally construct an end-to-end model for the detection and re-id sub-task, which decouples the model architecture for the two sub-tasks. The proposed task-incremental network allows task-incremental training for the two conflicting tasks. This enables independent learning for different objectives thus fully decoupled the model for persons earch. Comprehensive experimental evaluations demonstrate the effectiveness of the proposed fully decoupled models for end-to-end person search. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

DeepRicci: Self-supervised Graph Structure-Feature Co-Refinement for Alleviating Over-squashing

DeepRicci: Self-supervised Graph Structure-Feature Co-Refine...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Li Sun Zhenhao Huang Hua Wu Junda Ye Hao Peng Zhengtao Yu Philip S. Yu School of Control and Computer Engineering North China Electric Power University Beijing China School of Computer Science Beijing University of Posts and Telecommunications Beijing China State Key Laboratory of Software Development Environment Beihang University Beijing China Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming China Department of Computer Science University of Illinois at Chicago IL USA

Graph Neural Networks (GNNs) have shown great power for learning and mining on graphs, and Graph Structure Learning (GSL) plays an important role in boosting GNNs with a refined graph. In the literature, most GSL solutions either primarily focus on structure refinement with task-specific supervision (i.e., node classification), or overlook the inherent weakness of GNNs themselves (e.g., over-squashing), resulting in suboptimal performance despite sophisticated designs. In light of these limitations, we propose to study self-supervised graph structure-feature co-refinement for effectively alleviating the issue of over-squashing in typical GNNs. In this paper, we take a fundamentally different perspective of the Ricci curvature in Riemannian geometry, in which we encounter the challenges of modeling, utilizing and computing Ricci curvature. To tackle these challenges, we present a self-supervised Riemannian model, DeepRicci. Specifically, we introduce a latent Riemannian space of heterogeneous curvatures to model various Ricci curvatures, and propose a gyrovector feature mapping to utilize Ricci curvature for typical GNNs. Thereafter, we refine node features by geometric contrastive learning among different geometric views, and simultaneously refine graph structure by backward Ricci flow based on a novel formulation of differentiable Ricci curvature. Finally, extensive experiments on public datasets show the superiority of DeepRicci, and the connection between backward Ricci flow and over-squashing. Codes of our work are given in https://***/RiemanGraph/.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：